Object Recognition in Python and MNIST Dataset Modification and Recognition with Five Machine Learning Classifiers

Karayaneva, Yordanka; Hintea, Diana

doi:10.18178/joig.6.1.10-20

Cited by 52 publications

(11 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…They have used five machine learning algorithms, including neural networks and achieved 87%-98% accuracy on object recognition. 9 A combination of KNN and ANN is used for dragon fruit classification tasks. The study showed that the machine learning method had six times better performance than manual classification.…”

Section: Related Workmentioning

confidence: 99%

An efficient approach for age-wise rice seeds classification using SURF-BOF with modified cascaded-ANFIS algorithm

Rathnayake

Dang

Miyazaki

et al. 2023

Fifteenth International Conference on Machine Vision (ICMV 2022)

View full text Add to dashboard Cite

It is a well-known fact that the quality of a seed highly impacts the germination of a rice seed. The age of the seed is one of the primary key points in assessing the seed quality. Therefore, this study aims to develop an AI-based machine-learning model to classify age-wise rice seeds. This study employs the SURF-BOF-based Cascaded-ANFIS algorithm for the implementation of the classifier. The proposed model performances were compared to the VGG16. Moreover, this research contributes a novel Japanese rice seed dataset to the scientific community. Furthermore, a 10-Fold cross-validation is performed to evaluate the robustness of the novel approach. The K-fold cross-validation's mean accuracy confirmed the proposed algorithm's higher robustness in the age-wise classification of rice seeds. Nevertheless, the results were evaluated using the confusion matrix and metrics such as precision, recall, and F1-Score. The Accuracy of Akitakomachi, Koshihikari, Yandao-8, and rice variety classification is 99%, 99%, 92%, and 97%. Analysis of the results determines the ability to classify rice by age and the general robustness of the algorithm.

show abstract

Section: Related Workmentioning

confidence: 99%

An efficient approach for age-wise rice seeds classification using SURF-BOF with modified cascaded-ANFIS algorithm

Rathnayake

Dang

Miyazaki

et al. 2023

Fifteenth International Conference on Machine Vision (ICMV 2022)

View full text Add to dashboard Cite

show abstract

“…In the early stage of video understanding, researchers pay more attention to the features of manual design, which is the basis for encoding the appearance and motion information of video 16 . With the great success of deep neural network in Imagenet 17,18 and object recognition and detection 43,44,45 , many video recognition and classification methods begin to extract features from 2D image convolution network after video frame extraction, and explore the improvement of video classification effect in combination with video optical flow information 20,19,21 . Such methods often process RGB image frames and optical flow image frames respectively, and fuse the features before recognition.…”

Section: Related Workmentioning

confidence: 99%

Improved video classification method based on non-parametric attention combined with self-supervision

L²

2022

Fourteenth International Conference on Digital Image Processing (ICDIP 2022)

View full text Add to dashboard Cite

It is worth mentioning that in the video sequence modeling, the best recognition architecture is transformer. The current popular transformer based video classification methods focus on the importance of current features in time sequence. The degree of characterization of simultaneous order is insufficient, and simple data augmentation has unstable classification effect. In this paper we proposed a method of non-parametric attention combined with self-supervised feature construction to further improve video classification. In this method, the non-parametric attention mechanism is constructed in the simultaneous order feature to fit the multi-local extreme value distribution. At the same time, in the process of model learning, the input video is randomly masked in temporal domain and spatial domain, and selfsupervised information is added to effectively learn the details and classification information of video content. Experiments using kinetics400, kinetics600 and something V2 datasets show that the algorithm in this paper has better improvement in accuracy than the current optimal method.

show abstract

“…Image processing is a component of the system's lower-level image analysis or computer vision functionality. With the aid of deep learning (DL), fuzzy systems, and improved feature extraction procedures, etc., image processing has made significant advances in recent years [1][2][3][4]. Currently, transformer models are gaining popularity in computer vision tasks.…”

Section: Introductionmentioning

confidence: 99%

How certain are tansformers in image classification: uncertainty analysis with Monte Carlo dropout

Islam

Zabeen

Islam

et al. 2023

Fifteenth International Conference on Machine Vision (ICMV 2022)

View full text Add to dashboard Cite

Researchers have been inspired to implement transformer models in solving machine vision problems after their tremendous success with natural language tasks. Using the straightforward architecture and swift performance of transformers, a variety of computer vision problems can be solved with more ease and effectiveness. However, a comparative evaluation of their uncertainty in prediction has not been done yet. As we know, real world applications require a measure of uncertainty to produce accurate predictions, which allows researchers to handle uncertain inputs and special cases, in order to successfully prevent overfitting. Our study approaches the unexplored issue of uncertainty estimation among three popular and effective transformer models employed in computer vision, such as Vision Transformers (ViT), Swin Transformers (SWT), and Compact Convolutional Transformers (CCT). We conduct a comparative experiment to determine which particular architecture is the most reliable in image classification. We use dropouts at the inference phase in order to measure the uncertainty of these transformer models. This approach, commonly known as Monte Carlo Dropout (MCD), works well as a low-complexity estimation to compute uncertainty. The MCD-based CCT model is the least uncertain architecture in this classification task. Our proposed MCD-infused CCT model also yields the best results with 78.4% accuracy, while the SWT model with embedded MCD exhibits Pmaximum performance gain where the accuracy increased by almost 3% with the final result being 71.4%.

show abstract

Object Recognition in Python and MNIST Dataset Modification and Recognition with Five Machine Learning Classifiers

Cited by 52 publications

References 14 publications

An efficient approach for age-wise rice seeds classification using SURF-BOF with modified cascaded-ANFIS algorithm

An efficient approach for age-wise rice seeds classification using SURF-BOF with modified cascaded-ANFIS algorithm

Improved video classification method based on non-parametric attention combined with self-supervision

How certain are tansformers in image classification: uncertainty analysis with Monte Carlo dropout

Contact Info

Product

Resources

About